{"version":1,"type":"story","url":"https://digestai.news/story/openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary","json":"https://digestai.news/story/openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary.json","markdown":"https://digestai.news/story/openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary.md","slug":"openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary","headline":"OpenMobile-2 shows open-source smartphone agents can match proprietary models","summary":"Researchers from Nanjing University, SenseTime and other universities released OpenMobile-2, an open-source smartphone agent built on Qwen3.5 (9 billion parameters) and Qwen3.6 (27 billion parameters). They trained the agents in a simulated environment containing more than 110 apps, including rebuilt versions of 35 popular Chinese services such as Taobao, JD, DiDi and Meituan, plus global tools like Slack and Google Drive. By keeping the amount of training data constant and increasing app variety, the success rate on unseen applications rose from 60.7 % to 67.5 %.\n\nOn real Android devices the larger model achieved 59.6 points on SPA‑Bench, the highest score reported for any open model, and scored 79.9 points on AndroidWorld after reinforcement learning. Direct‑command shortcuts, when explicitly trained, added up to 10.3 percentage points of task completion while reducing steps by about five. The team generated roughly 11,600 example workflows and over 2,000 practice tasks, using Google’s Gemini 3.1 Pro as the teacher model. The authors claim OpenMobile-2 ranks near the top among current smartphone agents, though they note the direct‑command feature remains experimental.","keyPoints":["Training on over 110 simulated apps lifted unseen‑app success from 60.7 % to 67.5 %","Larger OpenMobile‑2 model scored 59.6 points on SPA‑Bench, best among open models","Direct commands improved task success by up to 10.3 percentage points and cut steps by about five"],"whyItMatters":"Demonstrates that app‑diversity, not just data volume, can close the performance gap between open and proprietary mobile AI agents, expanding accessible automation.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["SenseTime","Oppo","Google","Microsoft Research"],"models":["OpenMobile-2","Qwen3.5","Qwen3.6","Gemini 3.1 Pro","Gemini 3.5 Flash"],"people":[]},"firstPublishedAt":"2026-10-25T06:55:22Z","updatedAt":"2026-10-25T06:55:22Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"The Decoder","title":"OpenMobile-2 proves open-source smartphone agents can rival proprietary models","url":"https://the-decoder.com/openmobile-2-proves-open-source-smartphone-agents-can-rival-proprietary-models","publishedAt":"2026-10-25T06:55:22Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"OpenMobile-2 shows open-source smartphone agents can match proprietary models\", 25 October 2026, https://digestai.news/story/openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary","publisher":"Digest AI","title":"OpenMobile-2 shows open-source smartphone agents can match proprietary models","datePublished":"2026-10-25T06:55:22Z","url":"https://digestai.news/story/openmobile-2-shows-open-source-smartphone-agents-can-match-proprietary"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}